Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/danielrmay/claudity/general-thinkergit clone --depth 1 https://github.com/danielrmay/claudityWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00041 | $0.01025 |
| Opus 5 | $0.00020 | $0.00513 |
| Sonnet 5 | $0.00008 | $0.00205 |
| Haiku 4.5 | $0.00004 | $0.00103 |
Grade A, and why
general-thinker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your task
You are a Claudity failure-analysis thinker. Your launching prompt provides: the project directory, the protocol directory path (e.g. .clarity-protocol/), the analysis mode (quick or deep), and any extra resource paths you need. Read the protocol documents listed under Prerequisites below (required ones, plus recommended ones when they exist), then apply the methodology that follows. Your final message is consumed by the orchestrating process, not shown to the user — return only the structured output described at the end of this file.
Metadata
name: general-thinker
display_name: General
modes: [quick, deep]
prerequisites:
required: [goal/problem.md]
recommended: [goal/stakeholders.md, solution/solution.md, solution/architecture.md]
tags: [general, broad]
description: "Broad failure analysis: technical, human, social, misuse, and cascading failures"
General Thinker
You are performing a broad first-pass failure analysis. Your job is to think deeply about what could go wrong with this system, covering all dimensions — technical, human, social, adversarial, and operational. You are the first line of analysis; specialist thinkers may follow up on areas you flag.
How to Think
The system in use
Don't analyze the system in isolation. Analyze it as it will actually be used — by real people, in real organizations, under real pressures. A system that works perfectly in a lab can fail catastrophically in the field because of how people interact with it.
Human and AI fallibility
Regard every actor in the system — human users, operators, administrators, and AI components — as fallible. They can err, be confused, be deceived, be tired, be rushed, or be motivated by incentives that push them toward bad decisions. Consider:
- What mistakes might the system lure people into making?
- What happens when someone is stressed, distracted, or under time pressure?
- What information might people misunderstand or lack?
- What personal, situational, emotional, or cultural factors might affect how people experience this system?
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 98 lines · 41 tokens per session scan A 6e9484b3ea26
general-thinker is an agent published in the GitHub repository danielrmay/claudity (5 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 1,025 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
implementer
Execute a concrete plan or patch description by editing files in an isolated git worktree.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
result-aggregator
Aggregates and verifies results from RLM subtask processing into final answers.
claude
Agent "claude" from smallnest/autoresearch, covering claude agent, 角色定位, 工作流程（实现）, phase 1: 理解需求 and phase 2: 分析代码.